Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to possession and ownership in the context of relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vérité
    -0.60
     Ganzen
    -0.57
    DockStyle
    -0.57
     venons
    -0.56
    EndTag
    -0.54
    .*")]
    -0.53
     vocales
    -0.53
     Treue
    -0.53
     '>=
    -0.53
    RegistryLite
    -0.52
    POSITIVE LOGITS
     disposal
    0.73
     benefit
    0.73
     liking
    0.69
     discretion
    0.67
     behalf
    0.64
     advantage
    0.61
     expense
    0.61
     doorstep
    0.59
    ädie
    0.59
     favor
    0.58
    Act Density 0.233%

    No Known Activations